ADAPTIVE SEQUENTIAL SAMPLING FOR POLYNOMIAL CHAOS EXPANSION

Abstract

. The paper presents a sampling strategy created specifically for surrogate modeling via polynomial chaos expansion. The proposed method combines adaptivity of surrogate model and sequential sampling enabling one-by-one extension of an experimental design. The iteration process of sequential sampling selects from a large pool of candidate points by trying to cover the design domain proportionally to their local variance contribution. The criterion for the sample selection balances between exploitation of the surrogate model and exploration of the design domain. The obtained numerical results confirm its superiority over standard non-sequential approaches in terms of surrogate model accuracy and estimation of the output variance.